This repository contains the materials presented during the PhD Symposium of the XL International Congress of the Spanish Society for Natural Language Processing, including the three-minute presentation slide, the poster and the article related to the research paper.
- Elevator pitch slide: Slide used during the oral presentation, in PDF format, summarising the main points of the research.
- Poster: Poster presented at the poster session of the symposium, providing a visually appealing overview of the key results of the work.
- Paper: A research paper that details the research in depth, including methodology, results and conclusions.
Title: Leveraging Temporal Analysis to Predict the Impact of Political Messages on Social Media in Spanish
Abstract: Social networks such as TikTok, Facebook, or X introduce techniques to inform users if the content they are consuming may be fake. This, together with the account banning for hate speech or disinformation spread, is leading more and more pseudo-media in Spain to use Telegram to communicate with their audience. Thus, it is difficult to warn users about the veracity of the content, leading them to accept political disinformation as true if it aligns with their beliefs, which ultimately promotes their polarization. In this work, we want to identify the political messages that will have the greatest impact on people to recommend when it is necessary to initiate a refutation strategy if it is disinformative, so that refutation begins before disinformation is taken as true by a part of society. To estimate the impact of political messages, we take into account the polarization generated by them and their virality. Our main hypothesis is that this value is proportional to the time of publication, with the greatest impact in the most politically and socially sensitive contexts. Hence, our goal is to compile a dataset of political messages disseminated on Telegram (along with the generated responses) and its temporal context, in order to develop methods and metrics to identify the expected impact and when they might have the greatest impact.
The materials presented here can be used as a reference for future research, teaching, or for dissemination of the work presented at the symposium.
You can contact me through my email adress ibai.guillen@upm.es. Also, you can take a look to my personal webpage in case you want to know more about me.
This work is supported by the Predoctoral Grant (PIPF-2022/COM-25947) of the Consejería de Educación, Ciencia y Universidades de la Comunidad de Madrid, Spain.
This work is licensed under the MIT License. For more details, see the LICENSE file.